Aryanvs's workspace
Runs
4
State
Notes
User
Tags
Created
Runtime
Sweep
dataloader_arguments.dataloader_num_workers
dataloader_arguments.pin_memory
dataset_arguments.dataset_config
dataset_arguments.dataset_shuffle_buffer_size
dataset_arguments.enable_precomputation
dataset_arguments.precomputation_dir
dataset_arguments.precomputation_items
dataset_arguments.precomputation_once
diffusion_arguments.flow_base_seq_len
diffusion_arguments.flow_base_shift
diffusion_arguments.flow_logit_mean
diffusion_arguments.flow_logit_std
diffusion_arguments.flow_max_seq_len
diffusion_arguments.flow_max_shift
diffusion_arguments.flow_mode_scale
diffusion_arguments.flow_resolution_shifting
diffusion_arguments.flow_shift
diffusion_arguments.flow_weighting_scheme
miscellaneous_arguments.allow_tf32
miscellaneous_arguments.init_timeout
miscellaneous_arguments.logging_dir
miscellaneous_arguments.logging_steps
miscellaneous_arguments.nccl_timeout
miscellaneous_arguments.output_dir
miscellaneous_arguments.push_to_hub
miscellaneous_arguments.report_to
miscellaneous_arguments.tracker_name
miscellaneous_arguments.verbose
model_arguments.layerwise_upcasting_modules
model_arguments.layerwise_upcasting_skip_modules_pattern
model_arguments.layerwise_upcasting_storage_dtype
model_arguments.model_name
model_arguments.pretrained_model_name_or_path
model_arguments.text_encoder_2_dtype
model_arguments.text_encoder_3_dtype
model_arguments.text_encoder_dtype
model_arguments.transformer_dtype
model_arguments.vae_dtype
optimizer_arguments.beta1
optimizer_arguments.beta2
optimizer_arguments.epsilon
optimizer_arguments.lr
optimizer_arguments.lr_num_cycles
optimizer_arguments.lr_power
Finished
-
aryanvs
28s
-
0
false
examples/training/sft/cogview4/the_simpsons/training.json
32
false
/fsx/aryan/cogview4/precomputed
512
false
256
0.5
0
1
4096
1.15
1.29
false
1
logit_normal
false
600
logs
1
600
/fsx/aryan/cogview4
false
wandb
finetrainers-cogview4
0
[]
["patch_embed","pos_embed","x_embedder","context_embedder","^proj_in$","^proj_out$","norm"]
torch.float8_e4m3fn
cogview4
THUDM/CogView4-6B
torch.bfloat16
torch.bfloat16
torch.bfloat16
torch.bfloat16
torch.bfloat16
0.9
0.99
1.0000e-8
0.00001
1
1
Finished
-
aryanvs
14h 9m 53s
-
0
false
examples/training/sft/cogview4/the_simpsons/training.json
32
false
/fsx/aryan/cogview4/precomputed
512
false
256
0.5
0
1
4096
1.15
1.29
false
1
logit_normal
false
600
logs
1
600
/fsx/aryan/cogview4
false
wandb
finetrainers-cogview4
0
[]
["patch_embed","pos_embed","x_embedder","context_embedder","^proj_in$","^proj_out$","norm"]
torch.float8_e4m3fn
cogview4
THUDM/CogView4-6B
torch.bfloat16
torch.bfloat16
torch.bfloat16
torch.bfloat16
torch.bfloat16
0.9
0.99
1.0000e-8
0.00001
1
1
Finished
-
aryanvs
1d 48m 39s
-
0
false
examples/training/sft/cogview4/raider_white_tarot/training.json
32
-
/raid/aryan/cogview4/precomputed
120
true
256
0.5
0
1
4096
1.15
1.29
false
1
logit_normal
false
600
logs
1
600
/raid/aryan/cogview4
false
wandb
finetrainers-cogview4
0
[]
["patch_embed","pos_embed","x_embedder","context_embedder","^proj_in$","^proj_out$","norm"]
torch.float8_e4m3fn
cogview4
THUDM/CogView4-6B
torch.bfloat16
torch.bfloat16
torch.bfloat16
torch.bfloat16
torch.bfloat16
0.9
0.99
1.0000e-8
0.00003
1
1
Finished
-
aryanvs
8h 14m 56s
-
0
false
examples/training/sft/cogview4/raider_white_tarot/training.json
32
-
/raid/aryan/cogview4/precomputed
120
true
256
0.5
0
1
4096
1.15
1.29
false
1
logit_normal
false
600
logs
1
600
/raid/aryan/cogview4
false
wandb
finetrainers-cogview4
0
[]
["patch_embed","pos_embed","x_embedder","context_embedder","^proj_in$","^proj_out$","norm"]
torch.float8_e4m3fn
cogview4
THUDM/CogView4-6B
torch.bfloat16
torch.bfloat16
torch.bfloat16
torch.bfloat16
torch.bfloat16
0.9
0.99
1.0000e-8
0.00003
1
1
1-4
of 4